Improved prediction of bacterial transcription start sites

John J Gordon; Michael W Towsey; James M Hogan; Sarah A Mathews; Peter Timms

doi:10.1093/bioinformatics/bti771

Back

Improved prediction of bacterial transcription start sites

Journal article

Peer reviewed

Improved prediction of bacterial transcription start sites

John J Gordon, Michael W Towsey, James M Hogan, Sarah A Mathews and Peter Timms

Bioinformatics, Vol.22(2), pp.142-148

2006

DOI: https://doi.org/10.1093/bioinformatics/bti771

Files and links (1)

url

https://doi.org/10.1093/bioinformatics/bti771View

Published Version

Abstract

Mathematical Sciences

Biological Sciences

Information and Computing Sciences

bacterial promoters

support vector machines

Motivation: Identifying bacterial promoters is an important step toward understanding gene regulation. In this paper, we address the problem of predicting the location of promoters and their transcription start sites (TSSs) in Escherichia coli. The accepted method for this problem is to use position weight matrices (PWMs), which define conserved motifs at the sigma-factor binding site. However this method is known to result in a large numbers of false positive predictions. Results: Our approaches to TSS prediction are based upon an ensemble of support vector machines (SVMs) employing a variant of the mismatch string kernel. This classifier is sub-sequently combined with a PWM and a model based on distribution of distances from TSS to gene start. We investi-gate the effect of different scoring techniques and quantify performance using area under a detection-error tradeoff curve. When tested on a biologically realistic task, our method provides performance comparable or superior to the best reported for this task. False positives are significantly reduced, an improvement of great significance to biologists.

Details

Title: Improved prediction of bacterial transcription start sites
Authors: John J Gordon (Author) - Queensland University of Technology
Michael W Towsey (Author) - Queensland University of Technology
James M Hogan (Author) - Queensland University of Technology
Sarah A Mathews (Author) - Queensland University of Technology
Peter Timms (Author) - Queensland University of Technology
Publication details: Bioinformatics, Vol.22(2), pp.142-148
Publisher: Oxford University Press
DOI: 10.1093/bioinformatics/bti771
ISSN: 1367-4803
Organisation Unit: Centre for Bioinnovation; University of the Sunshine Coast, Queensland
Language: English
Record Identifier: 99449785402621
Output Type: Journal article

Metrics

349 Record Views

50 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Web Of Science research areas: Biochemical Research Methods; Biotechnology & Applied Microbiology; Computer Science, Interdisciplinary Applications; Mathematical & Computational Biology; Statistics & Probability

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

Source: InCites